Parabéns aos colaboradores do LAPISCO pelo trabalho intitulado “Detecting Parkinson’s disease with sustained phonation and speech signals using machine learning techniques” publicado no periódico Pattern Recognition Letter (Elsevier), JCR 1.95. . Abstract: This study investigates the processing of voice signals for detecting Parkinson’s disease. This disease is one of the neurological disorders that affect people in the world most. The approach evaluates the use of eighteen feature extraction techniques and four machine learning methods to classify data obtained from sustained phonation and speech tasks. Phonation relates to the vowel /a/ voicing task and speech to the pronunciation of a short sentence in Lithuanian language. TheRead More →

O PPGCC-IFCE realizou a sua 36a. defesa de mestrado no último dia 08/04/2019, sendo esta a 12a colaboração do LAPISCO no PPGCC-IFCE. O aluno Aldisio Gonçalves Medeiros obteve seu título de mestre em Ciência da Computação com o trabalho intitulado “Um novo método de contorno ativo geodésico rápido para segmentação de pulmão em imagens de Tomografia Computadorizada”. O trabalho foi orientado pelo Prof. Dr. Pedro Pedrosa Rebouças Filho (PPGCC-IFCE), e completaram a banca examinadora o Prof. Dr. Francisco Nivando Bezerra (PPGCC-IFCE) e o Prof. Dr. Antônio Carlos da Silva Barros (UNILAB).Read More →

Parabéns aos colaboradores do LAPISCO pelo trabalho intitulado “A Novel Electrocardiogram Feature Extraction Approach for Cardiac Arrhythmia Classification” publicado no periódico Future Generation Computer Systems (Elsevier), JCR 4.97. . Abstract: In this work, we propose a novel approach to detect cardiac arrhythmias in electrocardiograms (ECG). The proposal focuses on different feature extractors and machine learning methods. The feature extraction techniques evaluated were Fourier, Goertzel, Higher Order Statistics (HOS), and Structural Co-Occurrence Matrix (SCM). As far as the authors know, this is the first time that SCM has been applied to the feature extraction task with ECG signals. Four well-known classifiers, commonly referred to in theRead More →